jinaai/jina-embeddings-v2-small-en · Trust remote code = True, even for fine-tuned local model?

7 days ago

Hi guys,

From the SBERT documentation, I got the impression that I only needed to set trust_remote_code to True when using your model "directly" from the Hub. Yet, when I fine-tune it and save the model using model.save(output_dir) I can only access it whilst having trust_remote_code = True (whilst also having local_files_only = True).

When I try to ditch trust_remote_code I get a warning, and the embeddings become meaningless.

Any clues or things I should try?:))

tomaarsen

7 days ago

Hello!

Indeed - the reason that you're encountering this behaviour is because the code modeling files are stored outside of this repository, in https://huggingface.co/jinaai/jina-bert-implementation
They are loaded with these lines: https://huggingface.co/jinaai/jina-embeddings-v2-small-en/blob/main/config.json#L9-L12

To be able to ditch trust_remote_code, you must update the config.json of your local model to just e.g.:

    "AutoConfig": "configuration_bert.JinaBertConfig",
    "AutoModelForMaskedLM": "modeling_bert.JinaBertForMaskedLM",
    "AutoModel": "modeling_bert.JinaBertModel",
    "AutoModelForSequenceClassification": "modeling_bert.JinaBertForSequenceClassification"

And then download https://huggingface.co/jinaai/jina-bert-implementation/blob/main/modeling_bert.py and https://huggingface.co/jinaai/jina-bert-implementation/blob/main/configuration_bert.py and place them in the model repository. Then you won't need trust_remote_code.

Tom Aarsen

eMbeddr

7 days ago

Aha! Then it makes sense - thanks for the quick reply. And thanks for the solid work you're doing!:))

M